Research map / Video / Video segmentation and tracking
Restore From Restored: Video Restoration With Pseudo Clean Video
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Fine-tune VNLnet offline using pseudo-clean frames | VNLnet · Derf, σ=15 | PSNR: 36.33 -> 36.68 | Helped |
| Fine-tune VNLnet offline using pseudo-clean frames | VNLnet · Derf, σ=25 | PSNR: 33.77 -> 34.51 | Helped |
| Fine-tune VNLnet offline using pseudo-clean frames | VNLnet · Derf, σ=40 | PSNR: 30.49 -> 32.27 | Helped |
| Fine-tune VNLnet offline using pseudo-clean frames | VNLnet · DAVIS, σ=15 | PSNR: 37.37 -> 37.97 | Helped |
| Fine-tune VNLnet offline using pseudo-clean frames | VNLnet · DAVIS, σ=25 | PSNR: 34.28 -> 35.33 | Helped |
| Fine-tune VNLnet offline using pseudo-clean frames | VNLnet · DAVIS, σ=40 | PSNR: 31.13 -> 32.93 | Helped |
| Fine-tune RViDeNet offline using pseudo-clean frames | RViDeNet · CRVD | PSNR: 39.95 -> 40.13 | Helped |
| Use online restore-from-restored fine-tuning instead of the pretrained FastDVDnet baseline | FastDVDnet · Derf | PSNR | Helped |
| Use 10 offline update steps rather than no test-time fine-tuning | FastDVDnet · Derf and DAVIS | PSNR | Helped |
| Use restore-from-restored online fine-tuning rather than frame-to-frame training | DnCNN · Derf video with large motion | PSNR | Helped |
| Use frame-to-frame fine-tuning rather than the pretrained baseline | DnCNN · Derf, test and training noise both σ=25 | PSNR | No clear effect |
Closest papers by meaning
- Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable (CVPR 2025 · similarity 0.87)
- Omni-Kernel Network for Image Restoration (AAAI 2024 · similarity 0.86)
- MR-VNet: Media Restoration using Volterra Networks (CVPR 2024 · similarity 0.86)
- Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance (CVPR 2024 · similarity 0.86)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.86)
- FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.